libact: Pool-based Active Learning in Python

TL;DR

libact is an open-source Python package that simplifies implementing and experimenting with various active learning strategies, including an automatic strategy selection meta-algorithm, for broader accessibility.

Contribution

It introduces a unified interface for multiple active learning strategies and a meta-algorithm for automatic strategy selection, enhancing usability and flexibility.

Findings

Supports multiple active learning strategies

Includes a meta-algorithm for strategy selection

Provides an easy-to-use, unified interface

Abstract

libact is a Python package designed to make active learning easier for general users. The package not only implements several popular active learning strategies, but also features the active-learning-by-learning meta-algorithm that assists the users to automatically select the best strategy on the fly. Furthermore, the package provides a unified interface for implementing more strategies, models and application-specific labelers. The package is open-source on Github, and can be easily installed from Python Package Index repository.